You can deploy this model and start earning money today!

kaiyuyue/
sphere-encoder-models

Name: sphere-encoder-models
Availability: InStock

cc-by-nc-4.0

Views

No views yet

This repository contains the model weights and configuration files for the Sphere Encoder project.

[!Note] These model weights have been reproduced with the released code and yield slightly different evaluation results compared to those reported in the original paper.

Model Card

dataset	🤗 hf model repo	params
Animal-Faces	`sphere-l-af`	642M
Oxford-Flowers	`sphere-l-of`	948M
ImageNet	`sphere-l-imagenet`	950M
ImageNet	`sphere-xl-imagenet`	1.3B

Download model checkpoints and put them in ./workspace/experiments. The directory tree should look like this:

bash

./workspace/experiments/
├── sphere-l-af
    ├── ckpt/ep0999.pth
    |── config.json
├── sphere-l-of
|── sphere-l-imagenet
|── sphere-xl-imagenet

Evaluation Results

Evaluate ImageNet models with CFG = 1.4:

bash

# --job_dir can be
#   sphere-l-imagenet, or sphere-xl-imagenet

./run.sh eval.py \
  --job_dir sphere-xl-imagenet \
  --forward_steps 1 4 \
  --report_fid rfid gfid \
  --use_cfg True \
  --cfg_min 1.4 \
  --cfg_max 1.4 \
  --cfg_position combo \
  --rm_folder_after_eval True

The evaluation results will be saved in ./workspace/experiments/sphere-xl-imagenet/eval/:

dataset	model	steps	rFID ↓	gFID ↓	IS ↑
ImageNet 256x256	Sphere-L	1	0.62	15.69	274.5
	Sphere-L	4	-	4.78	259.1
	Sphere-XL	1	0.62	14.52	299.3
	Sphere-XL	4	-	4.05	266.0

Evaluate unconditional Animal-Faces model:

bash

./run.sh eval.py \
  --job_dir sphere-l-af \
  --forward_steps 1 4 \
  --report_fid gfid \
  --rm_folder_after_eval True

dataset	model	steps	rFID ↓	gFID ↓	IS ↑
Animal-Faces 256x256	Sphere-L	1	-	21.56	8.3
	Sphere-L	4	-	18.73	9.8

Evaluate Oxford-Flowers model with CFG = 1.4:

bash

./run.sh eval.py \
  --job_dir sphere-l-of \
  --forward_steps 1 4 \
  --report_fid gfid \
  --use_cfg True \
  --cfg_min 1.6 \
  --cfg_max 1.6 \
  --cfg_position combo \
  --num_eval_samples 51000 \
  --rm_folder_after_eval True \
  --cache_sampling_noise False \

--num_eval_samples = 51000 are set for 102 classes such that each class has 500 samples for evaluation on 8 gpus. Adjust them accordingly if you have different number of gpus or want to evaluate on different number of samples.

dataset	model	steps	rFID ↓	gFID ↓	IS ↑
Oxford-Flowers 256x256	Sphere-L	1	-	25.10	3.4
	Sphere-L	4	-	11.27	3.2

kaiyuyue/sphere-encoder-models

Model Card

Evaluation Results

kaiyuyue/
sphere-encoder-models